---
title: "Make a talking-avatar video — estimate"
method: POST
path: "/v1/avatars/videos/estimate"
tags: ["Talking videos"]
---

# Make a talking-avatar video — estimate

`POST /v1/avatars/videos/estimate`

## Request

- Base URL: `https://apihub.co.il`
- URL: `https://apihub.co.il/v1/avatars/videos/estimate`
- Auth: HTTP bearer

Price the request without executing it. Same body as `POST /v1/avatars/videos`.

## Request body

- object
  - `speed` number: Speaking speed with `script`
  - `title` string
  - `engine` 'avatar_iii' | 'avatar_iv' | 'avatar_v': avatar_v (the newest and most lifelike, the looks that support it — GET /v1/avatars says which) · avatar_iv (default: the newest that animates every photo and twin) · avatar_iii (cheaper, rougher). The price differs per engine — ask /estimate
  - `script` string: What the avatar says (up to 5,000 characters). Pauses: <break time="1s"/>
  - `consent` object: The rights / consent declaration for this likeness (or send consent_id)
    - `basis` 'own' | 'consent' | 'licensed': own = it is you / your content · consent = the person gave explicit permission · licensed = you hold the rights to this content
    - `locale` 'he' | 'en' | 'ru' | 'uk': Language the statement was shown in
    - `subject` 'self' | 'other': self = your own face / voice / video · other = another person who agreed
    - `accepted` true, required: You accept the consent statement for this scope (GET the text in the docs or the dashboard)
    - `subject_name` string: Required for `other`: the person's full name
  - `language` string: The script's language (our code, e.g. he, en, ru, uk) — an accent hint for multilingual voices
  - `voice_id` string: With `script`: a voice from GET /v1/voices (a digital twin speaks in its own voice when omitted)
  - `audio_url` string, uri: Or your own speech (mp3 / wav, up to 10 minutes) — a recording, or a voice-over from /v1/ai/voice
  - `avatar_id` string: Your avatar (GET /v1/avatars)
  - `image_url` string, uri: Or animate a photo directly, without saving an avatar (Avatar IV). Needs `consent`
  - `consent_id` string: A consent you recorded before (the dashboard records one when you tick the box)
  - `resolution` '720p' | '1080p' | '4k'
  - `aspect_ratio` '9:16' | '16:9' | '1:1' | '4:5' | '5:4' | 'auto'
  - `motion_prompt` string: Body motion and gestures, e.g. "gesturing with hands while presenting" (Avatar IV / V)
  - `expressiveness` 'low' | 'medium' | 'high': How lively a photo avatar is (Avatar IV)
  - `background_color` string

## Response `200`

Estimate

- Estimate
  - `operation` string
  - `estimated_credits` number
  - `credits_to_reserve` number
  - `estimated_usage` object
  - `note` string, nullable
  - `balance` object
    - `available` number
  - `sufficient` boolean

---

[API](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai.md) · [All operations](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai/llms.txt) · [OpenAPI document](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai/revisions/a8caa42835ce?raw)